yt_dlp/extractor/fujitv.py

   1 from .common import InfoExtractor
   2 from ..networking import HEADRequest
   3
   4
   5 class FujiTVFODPlus7IE(InfoExtractor):
   6     _VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/(?P<sid>[0-9a-z]{4})/(?P<id>[0-9a-z]+)'
   7     _BASE_URL = 'https://i.fod.fujitv.co.jp/'
   8     _BITRATE_MAP = {
   9         300: (320, 180),
  10         800: (640, 360),
  11         1200: (1280, 720),
  12         2000: (1280, 720),
  13         4000: (1920, 1080),
  14     }
  15
  16     _TESTS = [{
  17         'url': 'https://fod.fujitv.co.jp/title/5d40/5d40110076',
  18         'info_dict': {
  19             'id': '5d40110076',
  20             'ext': 'ts',
  21             'title': '#1318 『まる子、まぼろしの洋館を見る』の巻',
  22             'series': 'ちびまる子ちゃん',
  23             'series_id': '5d40',
  24             'description': 'md5:b3f51dbfdda162ac4f789e0ff4d65750',
  25             'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40110076_a.jpg',
  26         },
  27     }, {
  28         'url': 'https://fod.fujitv.co.jp/title/5d40/5d40810083',
  29         'info_dict': {
  30             'id': '5d40810083',
  31             'ext': 'ts',
  32             'title': '#1324 『まる子とオニの子』の巻／『結成！2月をムダにしない会』の巻',
  33             'description': 'md5:3972d900b896adc8ab1849e310507efa',
  34             'series': 'ちびまる子ちゃん',
  35             'series_id': '5d40',
  36             'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40810083_a.jpg'},
  37         'skip': 'Video available only in one week',
  38     }]
  39
  40     def _real_extract(self, url):
  41         series_id, video_id = self._match_valid_url(url).groups()
  42         self._request_webpage(HEADRequest(url), video_id)
  43         json_info = {}
  44         token = self._get_cookies(url).get('CT')
  45         if token:
  46             json_info = self._download_json(
  47                 f'https://fod-sp.fujitv.co.jp/apps/api/episode/detail/?ep_id={video_id}&is_premium=false',
  48                 video_id, headers={'x-authorization': f'Bearer {token.value}'}, fatal=False)
  49         else:
  50             self.report_warning(f'The token cookie is needed to extract video metadata. {self._login_hint("cookies")}')
  51         formats, subtitles = [], {}
  52         src_json = self._download_json(f'{self._BASE_URL}abrjson_v2/tv_android/{video_id}', video_id)
  53         for src in src_json['video_selector']:
  54             if not src.get('url'):
  55                 continue
  56             fmt, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, 'ts')
  57             for f in fmt:
  58                 f.update(dict(zip(('height', 'width'),
  59                                   self._BITRATE_MAP.get(f.get('tbr'), ()))))
  60             formats.extend(fmt)
  61             subtitles = self._merge_subtitles(subtitles, subs)
  62
  63         return {
  64             'id': video_id,
  65             'title': json_info.get('ep_title'),
  66             'series': json_info.get('lu_title'),
  67             'series_id': series_id,
  68             'description': json_info.get('ep_description'),
  69             'formats': formats,
  70             'subtitles': subtitles,
  71             'thumbnail': f'{self._BASE_URL}img/program/{series_id}/episode/{video_id}_a.jpg',
  72             '_format_sort_fields': ('tbr', ),
  73         }